© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65372
    Prev
    Next
    INDEX
    Explanations

    custom or homemade functions/methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    产åīį
    -0.07
    Ban
    -0.07
    CLK
    -0.07
    åij½éģĭ
    -0.07
    大夫
    -0.06
     Ban
    -0.06
    è¾¼ãģ¾
    -0.06
    ä¹ĭæģĭ
    -0.06
    avu
    -0.06
    shot
    -0.06
    POSITIVE LOGITS
     custom
    0.10
    custom
    0.10
     Custom
    0.09
    .custom
    0.09
    èĩªå®ļä¹ī
    0.09
    èĩªåĪ¶
    0.09
    /custom
    0.08
    Custom
    0.08
    _custom
    0.08
     homemade
    0.08
    Activations Density 1.338%

    No Known Activations